Implementasi Adaptive Neuro-Fuzzy Inference System PadaSistem Deteksi Kelelahan Mental Berbasis Sinyal Electroencephalogram

Penulis

  • Teguh Surya Darma Santoso Universitas Brawijaya, Malang
  • Edita Rosana Widasari Universitas Brawijaya, Malang

DOI:

https://doi.org/10.25126/jtiik.124

Kata Kunci:

ANFIS, EEG, Kelelahan Mental, Sistem Deteksi

Abstrak

Kelelahan mental merupakan fenomena umum pada pelajar dan pekerja yang ditandai dengan penurunan energi, motivasi, kemampuan kognitif dan lainnya. Jika tidak segera ditangani, maka dapat menyebabkan berbagai gangguan kesehatan fisik maupun mental dan meningkatkan resiko kecelakaan. Psikolog mengidentifikasi kelelahan mental melalui pengukuran secara subjektif dengan kuesioner atau pengukuran secara kognitif dengan tes kognitif. Namun, proses tersebut memerlukan waktu yang lama dan hasil pengukuran cenderung bersifat subjektif, rentan terhadap kesalahan dan kurang valid untuk pasien yang terbiasa dengan aktivitas kognitif. Oleh karena itu, penelitian ini mengusulkan implementasi metode Adaptive Neuro-Fuzzy Inference System pada sistem deteksi kelelahan mental berbasis sinyal electroencephalogram satu kanal untuk meningkatkan keakuratan diagnosis, efisiensi waktu dan kenyamanan pengguna. Sistem menggunakan metode normalisasi min-max, segmentasi, dekomposisi Discrete Wavelet Transform, dan ekstraksi fitur Power Percentage, Standard Deviation, Mean Absolute Value dari sinyal theta. Sistem dikemas dalam aplikasi Graphical User Interface berbasis MATLAB sehingga dapat menampilkan keluaran berupa grafik sinyal theta, nilai-nilai ekstraksi fitur, dan hasil diagnosis pada laptop pengguna. Sistem ini menghasilkan akurasi klasifikasi sebesar 90% dan rata-rata waktu komputasi mencapai 0,45 detik. Sistem ini dapat diandalkan dan digunakan sebagai alat validator tambahan untuk psikolog dalam mendiagnosis kelelahan mental.

 

Abstract

Mental fatigue is a common phenomenon in students and workers characterized by decreased energy, motivation, cognitive ability and more. If left untreated, it can lead to various physical and mental health problems and increase the risk of accidents. Psychologists identify mental fatigue through subjective measurements with questionnaires or cognitive measurements with cognitive tests. However, the process takes a long time and the measurement results tend to be subjective, prone to errors and less valid for patients who are accustomed to cognitive activities. Therefore, this study proposes the implementation of the Adaptive Neuro-Fuzzy Inference System method on a single-channel electroencephalogram signal-based mental fatigue detection system to improve diagnosis accuracy, time efficiency and user convenience. The system uses min-max normalization, segmentation, Discrete Wavelet Transform decomposition, and Power Percentage, Standard Deviation, Mean Absolute Value feature extraction methods from theta signals. The system is packaged in a MATLAB-based Graphical User Interface application so that it can display output in the form of theta signal graphs, feature extraction values, and diagnosis results on the user's laptop. The system produced a classification accuracy of 90% and an average computation time reached 0.45 seconds. The system is reliable and can be used as an additional validator tool for psychologists in diagnosing mental fatigue.

Downloads

Download data is not yet available.

Referensi

ABRAMSON, A., 2022, 1 Januari. Burnout and stress are everywhere. American Psychological Association. https://www.apa.org/monitor/2022/01/special-burnout-stress

CHOPRA, S., DHIMAN, G., SHARMA, A., SHABAZ, M., SHUKLA, P., & ARORA, M., 2021. Taxonomy of Adaptive Neuro-Fuzzy Inference System in Modern Engineering Sciences. Computational Intelligence and Neuroscience, 2021. https://doi.org/10.1155/2021/6455592.

HENDRAWAN, M. A. 2021. Mental Fatigue Detection Using Single-Channel Eeg. In Jurnal Sistem Informasi Dan Bisnis Cerdas (SIBC) (Vol. 14, Issue 2).

KHAKIM, Z., & KUSROHMANIAH, S., 2021. Dasar - Dasar Electroencephalography (EEG) bagi Riset Psikologi. Buletin Psikologi, 29(1), 92. https://doi.org/10.22146/buletinpsikologi.52328

LEVINE, D., 2020. Tips for overcoming mental exhaustion. US News & World Report. https://health.usnews.com/health-care/patient- advice/articles/overcoming-mental-exhaustion-tips

SETIAWAN, A., WIBAWA, A. D., PANE, E. S., & PURNOMO, M. H., 2019, Maret. EEG-based mental fatigue detection using cognitive tests and RVM classification. In 2019 International Conference of Artificial Intelligence and Information Technology (ICAIIT) (pp. 180-185). IEEE.

NOVITASARI, D. C., SUWANTO, B. M., & ASYHAR, A. H., 2019. Classification of EEG Signals using Fast Fourier Transform (FFT) and Adaptive Neuro-Fuzzy Inference System (ANFIS). Jurnal Matematika MANTIK, 5(1), 35-44.

TRAN, Y., CRAIG, A., CRAIG, R., CHAI, R., & NGUYEN, H., 2020. The influence of mental fatigue on brain activity: Evidence from a systematic review with meta-analyses. In Psychophysiology (Vol. 57, Issue 5). Blackwell Publishing Inc. https://doi.org/10.1111/psyp.13554

LM PSIKOLOGI UGM., 2021. Laporan Hasil Riset Mandiri Tingkat Academic Burnout Mahasiswa Klaster Sosio-Humaniora UGM: Meningkatkan Kesadaran akan Urgensi Fenomena Academic Burnout. LM Psikologi UGM. https://lm.psikologi.ugm.ac.id/2021/12/laporan-hasil-riset-mandiri-tingkat-academic-burnout-mahasiswa-klaster-sosio-humaniora-ugm-meningkatkan-kesadaran-akan-urgensi-fenomena-academic-burnout/

WANG, F., WAN, Y., LI, M., HUANG, H., Li, L., HOU, X., PAN, J., WEN, Z., & LI, J., 2023. Recent Advances in Fatigue Detection Algorithm Based on EEG. Intelligent Automation & Soft Computing, 35(3), 3573–3586. https://doi.org/10.32604/iasc.2023.029698.

YAACOB, H., HOSSAIN, F., SHARI, S., KHARE, S. K., OOI, C. P., & ACHARYA, U. R., 2023. Application of Artificial Intelligence Techniques for Brain–Computer Interface in Mental Fatigue Detection: A Systematic Review (2011–2022). IEEE Access, 11, 74736–74758. https://doi.org/10.1109/ACCESS.2023.3296382.

Diterbitkan

29-08-2025

Terbitan

Bagian

Ilmu Komputer

Cara Mengutip

Implementasi Adaptive Neuro-Fuzzy Inference System PadaSistem Deteksi Kelelahan Mental Berbasis Sinyal Electroencephalogram. (2025). Jurnal Teknologi Informasi Dan Ilmu Komputer, 12(4), 789-798. https://doi.org/10.25126/jtiik.124